Ophthalmic Images Research Articles

Unveiling the clinical incapabilities: a benchmarking study of GPT-4V(ision) for ophthalmic multimodal image analysis

PurposeTo evaluate the capabilities and incapabilities of a GPT-4V(ision)-based chatbot in interpreting ocular multimodal images.MethodsWe developed a digital ophthalmologist app using GPT-4V and evaluated its performance with a dataset (60...

Influence of Image Factors on the Performance of Ophthalmic Ultrasound Deep Learning Model

ObjectiveThis study aims to evaluate the impact of image factors on the performance of deep learning models used for ophthalmic ultrasound image diagnosis. MethodsA total of 3,373 ophthalmic ultrasound images are used to deeply evaluate the influence of image factors on the performance of deep learning classification models. Inceptionv3, Xception, and the fusion model Inceptionv3-Xception are used to explore how brightness, contrast, gain, noise, size, format, pseudo-color seven image-related factors affect the classification performance of the model. ResultsInceptionv3-Xception has advantages in the recognition accuracy of various image factors. When the image brightness changes, the model's performance shows a downward trend (0.5 vs. 1 vs. 1.8, ACC 95.73 vs. 97.06 vs. 93.54, P < 0.05). When the image contrast changes, the model's performance is comparable (0.5 vs. 1 vs. 1.2, ACC 96.23 vs. 96.95 vs. 97.45, P > 0.05). When the image gain drops to 50 dB, the model's accuracy decreases significantly (50 dB vs. 105 dB, ACC 96.49 vs. 97.57, P < 0.05). When Gaussian noise is added to the image, the model's performance gradually decreases (0.02 vs. 0, ACC 89.48vs97.06, P < 0.05). When the image size drops to 25% of the original image, the model's performance decreases significantly (25% vs. 100%, ACC 93.18 vs. 97.06, P < 0.01). When the image format changes, the model's recognition accuracy is similar (JPG vs. BMP vs. PNG, ACC 96.98 vs. 97.06 vs. 97.06, P > 0.05). The accuracy of the model in recognizing pseudo-color images decreases significantly compared to grayscale images (grayscale vs. pseudo-color, ACC 35.96 vs. 97.06). ConclusionThese results indicate that image quality greatly influences the model training process, and acquiring high-quality images is an important prerequisite for high recognition performance of the model. This study offers valuable insights for the improvement of other robust deep learning models for ophthalmic ultrasound image recognition.

Application and progress of artificial intelligence technology in the segmentation of hyperreflective foci in OCT images for ophthalmic disease research.

With the advancement of retinal imaging, hyperreflective foci (HRF) on optical coherence tomography (OCT) images have gained significant attention as potential biological biomarkers for retinal neuroinflammation. However, these biomarkers, represented by HRF, present pose challenges in terms of localization, quantification, and require substantial time and resources. In recent years, the progress and utilization of artificial intelligence (AI) have provided powerful tools for the analysis of biological markers. AI technology enables use machine learning (ML), deep learning (DL) and other technologies to precise characterization of changes in biological biomarkers during disease progression and facilitates quantitative assessments. Based on ophthalmic images, AI has significant implications for early screening, diagnostic grading, treatment efficacy evaluation, treatment recommendations, and prognosis development in common ophthalmic diseases. Moreover, it will help reduce the reliance of the healthcare system on human labor, which has the potential to simplify and expedite clinical trials, enhance the reliability and professionalism of disease management, and improve the prediction of adverse events. This article offers a comprehensive review of the application of AI in combination with HRF on OCT images in ophthalmic diseases including age-related macular degeneration (AMD), diabetic macular edema (DME), retinal vein occlusion (RVO) and other retinal diseases and presents prospects for their utilization.

Clinical predictive factors and imaging biomarkers of treatment response to half dose PDT in patients with chronic central serous chorioretinopathy

PurposeTo determine the clinical and imaging biomarkers of the response to half-dose photodynamic therapy (HD-PDT) in patients with central serous chorioretinopathy (CSC) MethodsClinical records and baseline ophthalmic images of 67 chronic CSC patients who underwent HD-PDT were assessed. In addition to demographic data, optical coherence tomography (OCT), fluorescein angiography (FA) and fundus autofluorescence (FAF) images were analyzed for specific biomarkers. The patients were categorized to early responder and late responder based on the time needed for complete resolution of subretinal fluid after PDT (less than 1 month vs. more than 1 month). The baseline clinical and imaging biomarkers were compared between the two groups. ResultsSeventy-three eyes of 67 patients were included in the study. The mean response time to PDT was 1.63 ± 1.48 months with 82.2% (60/73) of eyes categorized as early responder. The mean response time to PDT in delayed-response group was 4.15±1.51 months. In multivariate analysis, delayed response to PDT was associated with lacking history of systemic corticosteroid consumption, lacking history of pretreatment with eplerenone or acetazolamide before PDT and presence of hyperreflective foci in baseline OCT images (all p values < 0.05). There was no association between final visual outcome and late response to PDT. ConclusionThe presence of inflammatory biomarkers such as hyperreflective foci in baseline OCT images might be indicative of resistance to PDT. Moreover, the effect of pretreatment with mineralocorticoid antagonist on the response to PDT in chronic CSC should be explored in future prospective studies.

Interpretation of Clinical Retinal Images Using an Artificial Intelligence Chatbot

PurposeTo assess the performance of ChatGPT-4 in providing accurate diagnoses to retina teaching cases from OCTCases. DesignCross-sectional study. SubjectsRetina teaching cases from OCTCases. MethodsWe prompted a custom chatbot with 69 retina cases containing multimodal ophthalmic images, asking it to provide the most likely diagnosis. In a sensitivity analysis, we inputted increasing amounts of clinical information pertaining to each case until the chatbot achieved a correct diagnosis. We performed multivariable logistic regressions on Stata v17.0 (StataCorp LLC, College Station, Texas) to investigate associations between the amount of text-based information inputted per prompt and the odds of the chatbot achieving a correct diagnosis, adjusting for the laterality of cases, number of ophthalmic images inputted, and imaging modalities. Main Outcome MeasuresOur primary outcome was the proportion of cases for which the chatbot was able to provide a correct diagnosis. Our secondary outcome was the chatbot’s performance in relation to the amount of text-based information accompanying ophthalmic images. ResultsAcross 69 retina cases collectively containing 139 ophthalmic images, the chatbot was able to provide a definitive, correct diagnosis for 35 (50.7%) cases. The chatbot needed variable amounts of clinical information to achieve a correct diagnosis, where the entire patient description as presented by OCTCases was required for a majority of correctly diagnosed cases (23/35 cases, 65.7%). Relative to when the chatbot was only prompted with a patient’s age and sex, the chatbot achieved a higher odds of a correct diagnosis when prompted with an entire patient description (OR=10.1, 95%CI=[3.3, 30.3], p<0.01). Despite providing an incorrect diagnosis for 34 (49.3%) cases, the chatbot listed the correct diagnosis within its differential diagnosis for 7 (20.6%) of these incorrectly answered cases. ConclusionsThis custom chatbot was able to accurately diagnose approximately half of the retina cases requiring multimodal input, albeit relying heavily on text-based contextual information that accompanied ophthalmic images. The diagnostic ability of the chatbot in interpretation of multimodal imaging without text-based information is currently limited. The appropriate use of the chatbot in this setting is of utmost importance, given bioethical concerns.

Confidence-aware multi-modality learning for eye disease screening

Multi-modal ophthalmic image classification plays a key role in diagnosing eye diseases, as it integrates information from different sources to complement their respective performances. However, recent improvements have mainly focused on accuracy, often neglecting the importance of confidence and robustness in predictions for diverse modalities. In this study, we propose a novel multi-modality evidential fusion pipeline for eye disease screening. It provides a measure of confidence for each modality and elegantly integrates the multi-modality information using a multi-distribution fusion perspective. Specifically, our method first utilizes normal inverse gamma prior distributions over pre-trained models to learn both aleatoric and epistemic uncertainty for uni-modality. Then, the normal inverse gamma distribution is analyzed as the Student’s t distribution. Furthermore, within a confidence-aware fusion framework, we propose a mixture of Student’s t distributions to effectively integrate different modalities, imparting the model with heavy-tailed properties and enhancing its robustness and reliability. More importantly, the confidence-aware multi-modality ranking regularization term induces the model to more reasonably rank the noisy single-modal and fused-modal confidence, leading to improved reliability and accuracy. Experimental results on both public and internal datasets demonstrate that our model excels in robustness, particularly in challenging scenarios involving Gaussian noise and modality missing conditions. Moreover, our model exhibits strong generalization capabilities to out-of-distribution data, underscoring its potential as a promising solution for multimodal eye disease screening.

An Artificial Intelligence Driven Approach for Classification of Ophthalmic Images using Convolutional Neural Network: An Experimental Study.

Early disease detection is emphasized within ophthalmology now more than ever, and as a result, clinicians and innovators turn to deep learning to expedite accurate diagnosis and mitigate treatment delay. Efforts concentrate on the creation of deep learning systems that analyze clinical image data to detect disease-specific features with maximum sensitivity. Moreover, these systems hold promise of early accurate diagnosis and treatment of patients with common progressive diseases. DenseNet, ResNet, and VGG-16 are among a few of the deep learning Convolutional Neural Network (CNN) algorithms that have been introduced and are being investigated for potential application within ophthalmology. In this study, the authors sought to create and evaluate a novel ensembled deep learning CNN model that analyzes a dataset of shuffled retinal color fundus images (RCFIs) from eyes with various ocular disease features (cataract, glaucoma, diabetic retinopathy). Our aim was to determine (1) the relative performance of our finalized model in classifying RCFIs according to disease and (2) the diagnostic potential of the finalized model to serve as a screening test for specific diseases (cataract, glaucoma, diabetic retinopathy) upon presentation of RCFIs with diverse disease manifestations. We found adding convolutional layers to an existing VGG-16 model, which was named as a proposed model in this article that, resulted in significantly increased performance with 98% accuracy (p<0.05), including good diagnostic potential for binary disease detection in cataract, glaucoma, diabetic retinopathy. The proposed model was found to be suitable and accurate for a decision support system in Ophthalmology Clinical Framework.

FFA-GPT: an automated pipeline for fundus fluorescein angiography interpretation and question-answer

Fundus fluorescein angiography (FFA) is a crucial diagnostic tool for chorioretinal diseases, but its interpretation requires significant expertise and time. Prior studies have used Artificial Intelligence (AI)-based systems to assist FFA interpretation, but these systems lack user interaction and comprehensive evaluation by ophthalmologists. Here, we used large language models (LLMs) to develop an automated interpretation pipeline for both report generation and medical question-answering (QA) for FFA images. The pipeline comprises two parts: an image-text alignment module (Bootstrapping Language-Image Pre-training) for report generation and an LLM (Llama 2) for interactive QA. The model was developed using 654,343 FFA images with 9392 reports. It was evaluated both automatically, using language-based and classification-based metrics, and manually by three experienced ophthalmologists. The automatic evaluation of the generated reports demonstrated that the system can generate coherent and comprehensible free-text reports, achieving a BERTScore of 0.70 and F1 scores ranging from 0.64 to 0.82 for detecting top-5 retinal conditions. The manual evaluation revealed acceptable accuracy (68.3%, Kappa 0.746) and completeness (62.3%, Kappa 0.739) of the generated reports. The generated free-form answers were evaluated manually, with the majority meeting the ophthalmologists’ criteria (error-free: 70.7%, complete: 84.0%, harmless: 93.7%, satisfied: 65.3%, Kappa: 0.762–0.834). This study introduces an innovative framework that combines multi-modal transformers and LLMs, enhancing ophthalmic image interpretation, and facilitating interactive communications during medical consultation.

Geometric Correspondence-Based Multimodal Learning for Ophthalmic Image Analysis.

Color fundus photography (CFP) and Optical coherence tomography (OCT) images are two of the most widely used modalities in the clinical diagnosis and management of retinal diseases. Despite the widespread use of multimodal imaging in clinical practice, few methods for automated diagnosis of eye diseases utilize correlated and complementary information from multiple modalities effectively. This paper explores how to leverage the information from CFP and OCT images to improve the automated diagnosis of retinal diseases. We propose a novel multimodal learning method, named geometric correspondence-based multimodal learning network (GeCoM-Net), to achieve the fusion of CFP and OCT images. Specifically, inspired by clinical observations, we consider the geometric correspondence between the OCT slice and the CFP region to learn the correlated features of the two modalities for robust fusion. Furthermore, we design a new feature selection strategy to extract discriminative OCT representations by automatically selecting the important feature maps from OCT slices. Unlike the existing multimodal learning methods, GeCoM-Net is the first method that formulates the geometric relationships between the OCT slice and the corresponding region of the CFP image explicitly for CFP and OCT fusion. Experiments have been conducted on a large-scale private dataset and a publicly available dataset to evaluate the effectiveness of GeCoM-Net for diagnosing diabetic macular edema (DME), impaired visual acuity (VA) and glaucoma. The empirical results show that our method outperforms the current state-of-the-art multimodal learning methods by improving the AUROC score 0.4%, 1.9% and 2.9% for DME, VA and glaucoma detection, respectively.

Transforming Tele-Ophthalmology: Utilizing Cloud Computing for Remote Eye Care.

Tele-ophthalmology is gaining recognition for its role in improving eye care accessibility via cloud-based solutions. The Google Cloud Platform (GCP) Healthcare API enables secure and efficient management of medical image data such as high-resolution ophthalmic images. This study investigates cloud-based solutions' effectiveness in tele-ophthalmology, with a focus on GCP's role in data management, annotation, and integration for a novel imaging device. Leveraging the Integrating the Healthcare Enterprise (IHE) Eye Care profile, the cloud platform was utilized as a PACS and integrated with the Open Health Imaging Foundation (OHIF) Viewer for image display and annotation capabilities for ophthalmic images. The setup of a GCP DICOM storage and the OHIF Viewer facilitated remote image data analytics. Prolonged loading times and relatively large individual image file sizes indicated system challenges. Cloud platforms have the potential to ease distributed data analytics, as needed for efficient tele-ophthalmology scenarios in research and clinical practice, by providing scalable and secure image management solutions.

CLINICALLY RELEVANT POSTERIOR VITREOUS DETACHMENT STAGING USING CIRCUMPAPILLARY AND MACULAR VOLUME OPTICAL COHERENCE TOMOGRAPHY.

This study was designed to investigate retinal nerve fiber layer circumpapillary optical coherence tomography to determine posterior vitreous detachment (PVD) status and to develop a clinically relevant PVD grading scale based on retinal nerve fiber layer circumpapillary optical coherence tomography to determine the incidence of PVD by age and association with vitreomacular traction disorders. Ophthalmic images and medical records of patients with retinal diseases were retrospectively analyzed by three masked graders using retinal nerve fiber layer circumpapillary optical coherence tomography and macular optical coherence tomography. Based on PVD status, eyes were categorized into five newly defined PVD stages. Among 2002 eyes, PVD stages were as follows: A) 25 (1.25%); B) 725 (36.21%); C-) 248 (12.39%); C+) 151 (7.54%); D) 851 (42.51%); X) 2 (0.1%). Posterior vitreous detachment was correlated with advanced age (P < 0.0001). Limited separation or partial separation between lamella within the posterior vitreous cortex (Stage B) was noted early (68% of eyes <18 years). Overall, 34% of eyes >70 years did not exhibit complete PVD. Of 75 eyes with tractional vitreoretinal disorders, 64 (85.3%) were Stage C-/C+, identifying Stage C as the high-risk "complication" stage. Imaging analyses using retinal nerve fiber layer circumpapillary optical coherence tomography and macular optical coherence tomography scans in conjunction allow rapid assessment of the PVD stage. These techniques can assist clinicians and surgeons in counseling patients and planning surgical approaches. Observations confirmed the progression of PVD through predictable stages and the progression of PVD with age.

인공지능 기반 신생혈관성 나이관련황반변성 진단보조소프트웨어 사용자 인터페이스 개선 연구

With the recent development of Software as a Medical Device (SaMD), the significance of reducing use errors in medical devices is increasing. In this study, we conducted a formative evaluation of Artificial Intelligence (AI)-based software for ophthalmic image detection and diagnosis. The software automatically displays the presence or absence of neovascular age-related macular degeneration using fundus images to assist medical personnel in making diagnostic decisions. We aimed to find ways to reduce the number of use errors in formative evaluations. For this purpose, we conducted usability testing by performing tasks based on use scenarios for usability formative evaluations with intended users in their intended use environments, and then modified the user interface to reduce use errors. The initial formative evaluation revealed errors in utilizing the capture and dragand- drop functions for uploading fundus images, checking analysis results, and perform logout procedures. To reduce use errors, we improved the function by relocating the capture icon, displaying a hand-shaped cursor during dragging, inserting a fundus position guide, and eliminating the drag-and-drop function. We have also enhanced the design to present analytics results in a more intuitive manner and added a separate logout button to reduce the risk of use error. As a result, the number of use errors in the formative evaluation decreased from six to one in the summative evaluation. The development of ophthalmic image detection and diagnosis assistant software that reflects these improvements is expected to enhance user safety, usability, and reduce use errors.

Advancing systemic disease diagnosis through ophthalmic image‐based artificial intelligence

AbstractThe eye serves as a unique window into systemic health, offering clinicians a valuable opportunity for early detection and targeted treatment. Against this backdrop, advancements in artificial intelligence (AI) and ophthalmic imaging are converging to pave the way for more precise and predictive diagnostics. This review aims to elucidate the transformative role of AI in utilizing ophthalmic imaging for the detection and prediction of systemic diseases. We begin by introducing the advantages of the eye as a valuable tool for detecting systemic diseases. We also provide an overview of various ophthalmic imaging techniques that have proven useful in predicting systemic ailments. Then, we summarize two research patterns for analyzing ocular data, followed by the introduction of current AI applications using ophthalmic images that significantly increase diagnostic precision. Despite the promise, challenges such as data heterogeneity and model interpretability persist, which are also covered in this review. We conclude by discussing future directions and the immense potential these AI‐enabled approaches hold for revolutionizing healthcare. As AI technologies advance, their potential integration with ophthalmic imaging offers promising avenues for improving the diagnosis, prediction, and management of various systemic diseases, thereby contributing to the evolving landscape of integrated healthcare.

Accuracy of an Artificial Intelligence Chatbot’s Interpretation of Clinical Ophthalmic Images

Ophthalmology is reliant on effective interpretation of multimodal imaging to ensure diagnostic accuracy. The new ability of ChatGPT-4 (OpenAI) to interpret ophthalmic images has not yet been explored. To evaluate the performance of the novel release of an artificial intelligence chatbot that is capable of processing imaging data. This cross-sectional study used a publicly available dataset of ophthalmic cases from OCTCases, a medical education platform based out of the Department of Ophthalmology and Vision Sciences at the University of Toronto, with accompanying clinical multimodal imaging and multiple-choice questions. Across 137 available cases, 136 contained multiple-choice questions (99%). The chatbot answered questions requiring multimodal input from October 16 to October 23, 2023. The primary outcome was the accuracy of the chatbot in answering multiple-choice questions pertaining to image recognition in ophthalmic cases, measured as the proportion of correct responses. χ2 Tests were conducted to compare the proportion of correct responses across different ophthalmic subspecialties. A total of 429 multiple-choice questions from 136 ophthalmic cases and 448 images were included in the analysis. The chatbot answered 299 of multiple-choice questions correctly across all cases (70%). The chatbot's performance was better on retina questions than neuro-ophthalmology questions (77% vs 58%; difference = 18%; 95% CI, 7.5%-29.4%; χ21 = 11.4; P < .001). The chatbot achieved a better performance on nonimage-based questions compared with image-based questions (82% vs 65%; difference = 17%; 95% CI, 7.8%-25.1%; χ21 = 12.2; P < .001).The chatbot performed best on questions in the retina category (77% correct) and poorest in the neuro-ophthalmology category (58% correct). The chatbot demonstrated intermediate performance on questions from the ocular oncology (72% correct), pediatric ophthalmology (68% correct), uveitis (67% correct), and glaucoma (61% correct) categories. In this study, the recent version of the chatbot accurately responded to approximately two-thirds of multiple-choice questions pertaining to ophthalmic cases based on imaging interpretation. The multimodal chatbot performed better on questions that did not rely on the interpretation of imaging modalities. As the use of multimodal chatbots becomes increasingly widespread, it is imperative to stress their appropriate integration within medical contexts.

Novel Methods for Diagnosing Glaucoma: Segmenting Optic Discs and Cups using Ensemble Learning Algorithms and CDR Ratio Analysis

Glaucoma, a multifactorial group of eye diseases characterized by progressive damage to the Glaucoma, a group of progressive optic neuropathies, is a leading cause of irreversible blindness globally, affecting millions of individuals. This research addresses the critical task of glaucoma identification through the segmentation of the optic disc and optic cup using ensemble learning algorithms, Unet and Gnet. The study leverages the capabilities of these algorithms to enhance the accuracy of the segmentation process, a crucial step in early glaucoma detection. A meticulously curated dataset of ophthalmic images is utilized, with a focus on preprocessing techniques includes resizing, normalization, filtering and contrast enhancement process to optimize the input quality. The proposed architectures of Unet and Gnet, highlighting their suitability for segmenting the optic disc and cup. The experimental setup involves rigorous training, with an emphasis on fine-tuning the models for segmentation tasks. Evaluation metrics, including Dice coefficient and sensitivity, are employed to assess the precision of the segmentation results. The outcomes demonstrate the efficacy of ensemble Unet and Gnet. Consistently achieving accuracy levels surpassing 98.90% across various datasets, the suggested model demonstrates exceptional performance in accurately categorizing severe cases. The study concludes with insights into the potential clinical impact of improved optic disc and cup segmentation on early glaucoma diagnosis, emphasizing the significance of ensemble learning in advancing ophthalmic image analysis for medical applications.

Feasibility of cross-vendor linkage of ophthalmic images with electronic health record data: an analysis from the IRIS Registry®.

To link compliant, universal Digital Imaging and Communications in Medicine (DICOM) ophthalmic imaging data at the individual patient level with the American Academy of Ophthalmology IRIS® Registry (Intelligent Research in Sight). A retrospective study using de-identified EHR registry data. IRIS Registry records. DICOM files of several imaging modalities were acquired from two large retina ophthalmology practices. Metadata tags were extracted and harmonized to facilitate linkage to the IRIS Registry using a proprietary, heuristic patient-matching algorithm, adhering to HITRUST guidelines. Linked patients and images were assessed by image type and clinical diagnosis. Reasons for failed linkage were assessed by examining patients' records. Success rate of linking clinicoimaging and EHR data at the patient level. A total of 2 287 839 DICOM files from 54 896 unique patients were available. Of these, 1 937 864 images from 46 196 unique patients were successfully linked to existing patients in the registry. After removing records with abnormal patient names and invalid birthdates, the success linkage rate was 93.3% for images. 88.2% of all patients at the participating practices were linked to at least one image. Using identifiers from DICOM metadata, we created an automated pipeline to connect longitudinal real-world clinical data comprehensively and accurately to various imaging modalities from multiple manufacturers at the patient and visit levels. The process has produced an enriched and multimodal IRIS Registry, bridging the gap between basic research and clinical care by enabling future applications in artificial intelligence algorithmic development requiring large linked clinicoimaging datasets.

Uni4Eye++: A General Masked Image Modeling Multi-modal Pre-training Framework for Ophthalmic Image Classification and Segmentation.

A large-scale labeled dataset is a key factor for the success of supervised deep learning in most ophthalmic image analysis scenarios. However, limited annotated data is very common in ophthalmic image analysis, since manual annotation is time-consuming and labor-intensive. Self-supervised learning (SSL) methods bring huge opportunities for better utilizing unlabeled data, as they do not require massive annotations. To utilize as many unlabeled ophthalmic images as possible, it is necessary to break the dimension barrier, simultaneously making use of both 2D and 3D images as well as alleviating the issue of catastrophic forgetting. In this paper, we propose a universal self-supervised Transformer framework named Uni4Eye++ to discover the intrinsic image characteristic and capture domain-specific feature embedding in ophthalmic images. Uni4Eye++ can serve as a global feature extractor, which builds its basis on a Masked Image Modeling task with a Vision Transformer architecture. On the basis of our previous work Uni4Eye, we further employ an image entropy guided masking strategy to reconstruct more-informative patches and a dynamic head generator module to alleviate modality confusion. We evaluate the performance of our pre-trained Uni4Eye++ encoder by fine-tuning it on multiple downstream ophthalmic image classification and segmentation tasks. The superiority of Uni4Eye++ is successfully established through comparisons to other state-of-the-art SSL pre-training methods. Our code is available at Github1.

Impact of Artificial Intelligence on Diagnosing Eye Diseases – A Meta-analysis

The application of artificial intelligence (AI) in the field of ophthalmology has garnered significant attention for its potential to enhance the accuracy of eye disease diagnosis. This systematic review and meta-analysis aimed to comprehensively assess the impact of AI on diagnosing eye diseases through the synthesis of existing research. A systematic search of electronic databases was conducted to identify relevant studies in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses protocol. Eligible studies were those that reported the diagnostic accuracy of AI in ophthalmic image diagnosis. The standardized mean difference (SMD) and mean difference (MD) were utilised as the effect size measures to evaluate AI performance. A total of 18 studies meeting the inclusion criteria were selected for the quantitative synthesis. Further, the meta-analysis revealed that AI exhibited a substantial positive impact on the accuracy of diagnosing eye diseases. The overall SMD across various diagnostic parameters indicated a statistically significant improvement (SMD = 0.88, 95% confidence interval [CI]: 0.71–1.05). Moreover, the MD of diagnostic values demonstrated significant enhancements, with an overall MD of −10.2 (95% CI: −12.1 to −8.3). The selected studies consistently demonstrated that AI achieved high accuracy levels, reinforcing its potential as a valuable tool in ophthalmic diagnosis. This study provides significant evidence supporting the significant positive impact of AI on diagnosing eye diseases. The synthesis of the selected studies underscores the high accuracy achieved by AI in ophthalmic image diagnosis, as indicated by the substantial SMD and MD improvements. These findings highlight the promising role of AI in ophthalmology, offering the potential to revolutionise the field and improve patient care through enhanced diagnostic precision.

Fundus-DeepNet: Multi-label deep learning classification system for enhanced detection of multiple ocular diseases through data fusion of fundus images

Detecting multiple ocular diseases in fundus images is crucial in ophthalmic diagnosis. This study introduces the Fundus-DeepNet system, an automated multi-label deep learning classification system designed to identify multiple ocular diseases by integrating feature representations from pairs of fundus images (e.g., left and right eyes). The study initiates with a comprehensive image pre-processing procedure, including circular border cropping, image resizing, contrast enhancement, noise removal, and data augmentation. Subsequently, discriminative deep feature representations are extracted using multiple deep learning blocks, namely the High-Resolution Network (HRNet) and Attention Block, which serve as feature descriptors. The SENet Block is then applied to further enhance the quality and robustness of feature representations from a pair of fundus images, ultimately consolidating them into a single feature representation. Finally, a sophisticated classification model, known as a Discriminative Restricted Boltzmann Machine (DRBM), is employed. By incorporating a Softmax layer, this DRBM is adept at generating a probability distribution that specifically identifies eight different ocular diseases. Extensive experiments were conducted on the challenging Ophthalmic Image Analysis-Ocular Disease Intelligent Recognition (OIA-ODIR) dataset, comprising diverse fundus images depicting eight different ocular diseases. The Fundus-DeepNet system demonstrated F1-scores, Kappa scores, AUC, and final scores of 88.56 %, 88.92 %, 99.76 %, and 92.41 % in the off-site test set, and 89.13 %, 88.98 %, 99.86 %, and 92.66 % in the on-site test set.In summary, the Fundus-DeepNet system exhibits outstanding proficiency in accurately detecting multiple ocular diseases, offering a promising solution for early diagnosis and treatment in ophthalmology.

Unobtrusive biometric data de-identification of fundus images using latent space disentanglement.

With the incremental popularity of ophthalmic imaging techniques, anonymization of the clinical image datasets is becoming a critical issue, especially the fundus images, which would have unique patient-specific biometric content. Towards achieving a framework to anonymize ophthalmic images, we propose an image-specific de-identification method on the vascular structure of retinal fundus images while preserving important clinical features such as hard exudates. Our method calculates the contribution of latent code in latent space to the vascular structure by computing the gradient map of the generated image with respect to latent space and then by computing the overlap between the vascular mask and the gradient map. The proposed method is designed to specifically target and effectively manipulate the latent code with the highest contribution score in vascular structures. Extensive experimental results show that our proposed method is competitive with other state-of-the-art approaches in terms of identity similarity and lesion similarity, respectively. Additionally, our approach allows for a better balance between identity similarity and lesion similarity, thus ensuring optimal performance in a trade-off manner.